Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 14899
    Prev
    Next
    INDEX
    Explanations

    various types of structured data or references related to error messages and notifications in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.83
    actéristi
    -0.79
    ſem
    -0.76
    IntoConstraints
    -0.73
    AutoScaleMode
    -0.72
    ſſen
    -0.71
    fjspx
    -0.70
    mybatisplus
    -0.69
    orsz
    -0.69
    ſſel
    -0.69
    POSITIVE LOGITS
    <eos>
    0.86
    ↵↵
    0.76
    ↵
    0.67
    ↵↵↵
    0.62
     etc
    0.62
    </blockquote>
    0.56
    </tr>
    0.55
     />;
    0.52
    ");
    0.52
    ))));
    0.51
    Activations Density 0.515%

    No Known Activations